{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PZMHP7F6BS22T5RIU3WQYBDRIL","short_pith_number":"pith:PZMHP7F6","canonical_record":{"source":{"id":"2305.11747","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T15:36:27Z","cross_cats_sorted":[],"title_canon_sha256":"02c763aec9d5064d1eb7c18dc6d5ef2353725ebd3ac15a51fe90a68e654d8580","abstract_canon_sha256":"0a44b785a21811afc6c3ac560b93ae1076151577b2314d7d166d58ac438d68d5"},"schema_version":"1.0"},"canonical_sha256":"7e5877fcbe0cb5a9f628a6ed0c047142cd8c2f90658a303daba4da98ac33aa42","source":{"kind":"arxiv","id":"2305.11747","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11747","created_at":"2026-07-05T07:03:24Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11747v3","created_at":"2026-07-05T07:03:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11747","created_at":"2026-07-05T07:03:24Z"},{"alias_kind":"pith_short_12","alias_value":"PZMHP7F6BS22","created_at":"2026-07-05T07:03:24Z"},{"alias_kind":"pith_short_16","alias_value":"PZMHP7F6BS22T5RI","created_at":"2026-07-05T07:03:24Z"},{"alias_kind":"pith_short_8","alias_value":"PZMHP7F6","created_at":"2026-07-05T07:03:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PZMHP7F6BS22T5RIU3WQYBDRIL","target":"record","payload":{"canonical_record":{"source":{"id":"2305.11747","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T15:36:27Z","cross_cats_sorted":[],"title_canon_sha256":"02c763aec9d5064d1eb7c18dc6d5ef2353725ebd3ac15a51fe90a68e654d8580","abstract_canon_sha256":"0a44b785a21811afc6c3ac560b93ae1076151577b2314d7d166d58ac438d68d5"},"schema_version":"1.0"},"canonical_sha256":"7e5877fcbe0cb5a9f628a6ed0c047142cd8c2f90658a303daba4da98ac33aa42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:24.877642Z","signature_b64":"o/gZVjBatFb7BFtj8Zjz6hqSx5ehsbsW1KJJcNQGRUJUo6lMn3wTQh46GFaJTBGwNUGYtVGaFjZSJyPw85LiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e5877fcbe0cb5a9f628a6ed0c047142cd8c2f90658a303daba4da98ac33aa42","last_reissued_at":"2026-07-05T07:03:24.877151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:24.877151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.11747","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:03:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TwKE1wbjymCp4nqK2Q8fQodnBi3NV3R0BAuupyPL8fAYiuWnGqFlobkzpPoUjSJDgLgRVoLHXXeA8KUo2xsGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:08:23.116634Z"},"content_sha256":"7031532342508fb29b6c4f8e51f76ce2769798acd5af9e20d7f4f7e8ad6ddf4b","schema_version":"1.0","event_id":"sha256:7031532342508fb29b6c4f8e51f76ce2769798acd5af9e20d7f4f7e8ad6ddf4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PZMHP7F6BS22T5RIU3WQYBDRIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jian-Yun Nie, Ji-Rong Wen, Junyi Li, Wayne Xin Zhao, Xiaoxue Cheng","submitted_at":"2023-05-19T15:36:27Z","abstract_excerpt":"Large language models (LLMs), such as ChatGPT, are prone to generate hallucinations, i.e., content that conflicts with the source or cannot be verified by the factual knowledge. To understand what types of content and to which extent LLMs are apt to hallucinate, we introduce the Hallucination Evaluation benchmark for Large Language Models (HaluEval), a large collection of generated and human-annotated hallucinated samples for evaluating the performance of LLMs in recognizing hallucination. To generate these samples, we propose a ChatGPT-based two-step framework, i.e., sampling-then-filtering. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11747","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.11747/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:03:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FmY9t4KtCmPbVy0JXtBx8YliTDzP6o2PyAAhf4ernmUREGsf/oTTWoB3n0JVTdRqVCkHOBHP5mb667ec4xdNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:08:23.117014Z"},"content_sha256":"4904280d8176900d259d1b259a9ecb92bc615d7f2d7c2afd524e958519f54164","schema_version":"1.0","event_id":"sha256:4904280d8176900d259d1b259a9ecb92bc615d7f2d7c2afd524e958519f54164"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZMHP7F6BS22T5RIU3WQYBDRIL/bundle.json","state_url":"https://pith.science/pith/PZMHP7F6BS22T5RIU3WQYBDRIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZMHP7F6BS22T5RIU3WQYBDRIL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T00:08:23Z","links":{"resolver":"https://pith.science/pith/PZMHP7F6BS22T5RIU3WQYBDRIL","bundle":"https://pith.science/pith/PZMHP7F6BS22T5RIU3WQYBDRIL/bundle.json","state":"https://pith.science/pith/PZMHP7F6BS22T5RIU3WQYBDRIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZMHP7F6BS22T5RIU3WQYBDRIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PZMHP7F6BS22T5RIU3WQYBDRIL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0a44b785a21811afc6c3ac560b93ae1076151577b2314d7d166d58ac438d68d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T15:36:27Z","title_canon_sha256":"02c763aec9d5064d1eb7c18dc6d5ef2353725ebd3ac15a51fe90a68e654d8580"},"schema_version":"1.0","source":{"id":"2305.11747","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11747","created_at":"2026-07-05T07:03:24Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11747v3","created_at":"2026-07-05T07:03:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11747","created_at":"2026-07-05T07:03:24Z"},{"alias_kind":"pith_short_12","alias_value":"PZMHP7F6BS22","created_at":"2026-07-05T07:03:24Z"},{"alias_kind":"pith_short_16","alias_value":"PZMHP7F6BS22T5RI","created_at":"2026-07-05T07:03:24Z"},{"alias_kind":"pith_short_8","alias_value":"PZMHP7F6","created_at":"2026-07-05T07:03:24Z"}],"graph_snapshots":[{"event_id":"sha256:4904280d8176900d259d1b259a9ecb92bc615d7f2d7c2afd524e958519f54164","target":"graph","created_at":"2026-07-05T07:03:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.11747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs), such as ChatGPT, are prone to generate hallucinations, i.e., content that conflicts with the source or cannot be verified by the factual knowledge. To understand what types of content and to which extent LLMs are apt to hallucinate, we introduce the Hallucination Evaluation benchmark for Large Language Models (HaluEval), a large collection of generated and human-annotated hallucinated samples for evaluating the performance of LLMs in recognizing hallucination. To generate these samples, we propose a ChatGPT-based two-step framework, i.e., sampling-then-filtering. ","authors_text":"Jian-Yun Nie, Ji-Rong Wen, Junyi Li, Wayne Xin Zhao, Xiaoxue Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T15:36:27Z","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11747","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7031532342508fb29b6c4f8e51f76ce2769798acd5af9e20d7f4f7e8ad6ddf4b","target":"record","created_at":"2026-07-05T07:03:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0a44b785a21811afc6c3ac560b93ae1076151577b2314d7d166d58ac438d68d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T15:36:27Z","title_canon_sha256":"02c763aec9d5064d1eb7c18dc6d5ef2353725ebd3ac15a51fe90a68e654d8580"},"schema_version":"1.0","source":{"id":"2305.11747","kind":"arxiv","version":3}},"canonical_sha256":"7e5877fcbe0cb5a9f628a6ed0c047142cd8c2f90658a303daba4da98ac33aa42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e5877fcbe0cb5a9f628a6ed0c047142cd8c2f90658a303daba4da98ac33aa42","first_computed_at":"2026-07-05T07:03:24.877151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:24.877151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o/gZVjBatFb7BFtj8Zjz6hqSx5ehsbsW1KJJcNQGRUJUo6lMn3wTQh46GFaJTBGwNUGYtVGaFjZSJyPw85LiDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:24.877642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11747","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7031532342508fb29b6c4f8e51f76ce2769798acd5af9e20d7f4f7e8ad6ddf4b","sha256:4904280d8176900d259d1b259a9ecb92bc615d7f2d7c2afd524e958519f54164"],"state_sha256":"b0bdae7b4170d8c04b3b4cc72914c33f02a11fdbff550884d6c62e499de73e2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r2XYGQp89pudfR5EJmkNVfNVc12Kt9yCcPEm/+c4skyPE+tvA02yuj5LICcX030ahKZbAgbmZTr6nyPU3IpDBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:08:23.129731Z","bundle_sha256":"8340650a7d140f1aed7b0f4a6d446b56cbf2a59b50bc2c8e234448902266bf96"}}